edbeeching's picture
edbeeching HF staff
Upload eval_results/HuggingFaceH4/mistral-7b-ift/v41.3/ifeval/results_2024-03-08T13-43-04.155641.json with huggingface_hub
89b85f8 verified
raw
history blame
2.47 kB
{
"config_general": {
"lighteval_sha": "?",
"num_fewshot_seeds": 1,
"override_batch_size": 4,
"max_samples": null,
"job_id": "",
"start_time": 11063.799488852,
"end_time": 11680.953573861,
"total_evaluation_time_secondes": "617.1540850089987",
"model_name": "HuggingFaceH4/mistral-7b-ift",
"model_sha": "12b119c990775414b28652b1a8c020aa5ef4795d",
"model_dtype": "torch.bfloat16",
"model_size": "13.99 GB",
"config": null
},
"results": {
"custom|ifeval|0": {
"prompt_level_strict_acc": 0.4011090573012939,
"prompt_level_strict_acc_stderr": 0.02109153689552074,
"inst_level_strict_acc": 0.5155875299760192,
"inst_level_strict_acc_stderr": 0.0005351140613637106,
"prompt_level_loose_acc": 0.43807763401109057,
"prompt_level_loose_acc_stderr": 0.021350931135490938,
"inst_level_loose_acc": 0.552757793764988,
"inst_level_loose_acc_stderr": 0.0005241147055349515
}
},
"versions": {
"custom|ifeval|0": 0
},
"config_tasks": {
"custom|ifeval": {
"name": "ifeval",
"prompt_function": "ifeval_prompt",
"hf_repo": "wis-k/instruction-following-eval",
"hf_subset": "default",
"metric": [
"ifeval_metric"
],
"hf_avail_splits": [
"train"
],
"evaluation_splits": [
"train"
],
"few_shots_split": "train",
"few_shots_select": "random_sampling",
"generation_size": 1280,
"stop_sequence": [],
"output_regex": null,
"frozen": false,
"suite": [
"custom"
],
"original_num_docs": 541,
"effective_num_docs": 541
}
},
"summary_tasks": {
"custom|ifeval|0": {
"hashes": {
"hash_examples": "e99cbf567588d7c6",
"hash_full_prompts": "46932ca113ba6b0c",
"hash_input_tokens": "8b2e0300fbfb70bc",
"hash_cont_tokens": "6d97bfd3542de6c2"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"effective_few_shots": 0.0,
"num_truncated_few_shots": 0
}
},
"summary_general": {
"hashes": {
"hash_examples": "ea046ab2c6fc5928",
"hash_full_prompts": "8ed52f7b74eb0590",
"hash_input_tokens": "9f4b7e9e7ff95d4a",
"hash_cont_tokens": "eadb0cd726ebfbec"
},
"truncated": 0,
"non_truncated": 541,
"padded": 0,
"non_padded": 541,
"num_truncated_few_shots": 0
}
}